AI agents use update-partial-view to create or update resources in Mcp Dev — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Dev environment.
This tool modifies partial views, which are code templates that control page rendering in Umbraco CMS. While reversible (not Destructive), unauthorized updates could inject malicious code into the website's rendering layer, affecting all users. This is a Write operation with significant blast radius due to the code-level impact on the CMS application.
From the tool's definition Tool name 'update-partial-view' and description 'Updates a partial view' indicate modification of application code/templates.
Attacks that exploit this kind of access
Updates a partial view. It is categorised as a Write tool in the Mcp Dev MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Dev MCP server in PolicyLayer and add a rule for update-partial-view: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mcp Dev. Nothing to install.
update-partial-view is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the update-partial-view rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for update-partial-view. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
update-partial-view is provided by the Mcp Dev MCP server (@umbraco-cms/mcp-dev). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →